DTDが欲しかったのだけど、見つけられ無かったので書いた。
http://www.w3.org/TR/html4/sgml/entities.html
の記事を
<?php $regexp = '@<!ENTITY\s+(\w+)\s+CDATA\s+"&#(\d+);"[^>]+>@smU'; preg_match_all($regexp, $ここにさっきのURLの記事, $m);
で抜き出して整形しただけ
数字参照(10進数) | 数字参照(16進数) | 文字実体参照 |
---|---|---|
160 | a0 | nbsp |
161 | a1 | iexcl |
162 | a2 | cent |
163 | a3 | pound |
164 | a4 | curren |
165 | a5 | yen |
166 | a6 | brvbar |
167 | a7 | sect |
168 | a8 | uml |
169 | a9 | copy |
170 | aa | ordf |
171 | ab | laquo |
172 | ac | not |
173 | ad | shy |
174 | ae | reg |
175 | af | macr |
176 | b0 | deg |
177 | b1 | plusmn |
178 | b2 | sup2 |
179 | b3 | sup3 |
180 | b4 | acute |
181 | b5 | micro |
182 | b6 | para |
183 | b7 | middot |
184 | b8 | cedil |
185 | b9 | sup1 |
186 | ba | ordm |
187 | bb | raquo |
188 | bc | frac14 |
189 | bd | frac12 |
190 | be | frac34 |
191 | bf | iquest |
192 | c0 | Agrave |
193 | c1 | Aacute |
194 | c2 | Acirc |
195 | c3 | Atilde |
196 | c4 | Auml |
197 | c5 | Aring |
198 | c6 | AElig |
199 | c7 | Ccedil |
200 | c8 | Egrave |
201 | c9 | Eacute |
202 | ca | Ecirc |
203 | cb | Euml |
204 | cc | Igrave |
205 | cd | Iacute |
206 | ce | Icirc |
207 | cf | Iuml |
208 | d0 | ETH |
209 | d1 | Ntilde |
210 | d2 | Ograve |
211 | d3 | Oacute |
212 | d4 | Ocirc |
213 | d5 | Otilde |
214 | d6 | Ouml |
215 | d7 | times |
216 | d8 | Oslash |
217 | d9 | Ugrave |
218 | da | Uacute |
219 | db | Ucirc |
220 | dc | Uuml |
221 | dd | Yacute |
222 | de | THORN |
223 | df | szlig |
224 | e0 | agrave |
225 | e1 | aacute |
226 | e2 | acirc |
227 | e3 | atilde |
228 | e4 | auml |
229 | e5 | aring |
230 | e6 | aelig |
231 | e7 | ccedil |
232 | e8 | egrave |
233 | e9 | eacute |
234 | ea | ecirc |
235 | eb | euml |
236 | ec | igrave |
237 | ed | iacute |
238 | ee | icirc |
239 | ef | iuml |
240 | f0 | eth |
241 | f1 | ntilde |
242 | f2 | ograve |
243 | f3 | oacute |
244 | f4 | ocirc |
245 | f5 | otilde |
246 | f6 | ouml |
247 | f7 | divide |
248 | f8 | oslash |
249 | f9 | ugrave |
250 | fa | uacute |
251 | fb | ucirc |
252 | fc | uuml |
253 | fd | yacute |
254 | fe | thorn |
255 | ff | yuml |
402 | 192 | fnof |
913 | 391 | Alpha |
914 | 392 | Beta |
915 | 393 | Gamma |
916 | 394 | Delta |
917 | 395 | Epsilon |
918 | 396 | Zeta |
919 | 397 | Eta |
920 | 398 | Theta |
921 | 399 | Iota |
922 | 39a | Kappa |
923 | 39b | Lambda |
924 | 39c | Mu |
925 | 39d | Nu |
926 | 39e | Xi |
927 | 39f | Omicron |
928 | 3a0 | Pi |
929 | 3a1 | Rho |
931 | 3a3 | Sigma |
932 | 3a4 | Tau |
933 | 3a5 | Upsilon |
934 | 3a6 | Phi |
935 | 3a7 | Chi |
936 | 3a8 | Psi |
937 | 3a9 | Omega |
945 | 3b1 | alpha |
946 | 3b2 | beta |
947 | 3b3 | gamma |
948 | 3b4 | delta |
949 | 3b5 | epsilon |
950 | 3b6 | zeta |
951 | 3b7 | eta |
952 | 3b8 | theta |
953 | 3b9 | iota |
954 | 3ba | kappa |
955 | 3bb | lambda |
956 | 3bc | mu |
957 | 3bd | nu |
958 | 3be | xi |
959 | 3bf | omicron |
960 | 3c0 | pi |
961 | 3c1 | rho |
962 | 3c2 | sigmaf |
963 | 3c3 | sigma |
964 | 3c4 | tau |
965 | 3c5 | upsilon |
966 | 3c6 | phi |
967 | 3c7 | chi |
968 | 3c8 | psi |
969 | 3c9 | omega |
977 | 3d1 | thetasym |
978 | 3d2 | upsih |
982 | 3d6 | piv |
8226 | 2022 | bull |
8230 | 2026 | hellip |
8242 | 2032 | prime |
8243 | 2033 | Prime |
8254 | 203e | oline |
8260 | 2044 | frasl |
8472 | 2118 | weierp |
8465 | 2111 | image |
8476 | 211c | real |
8482 | 2122 | trade |
8501 | 2135 | alefsym |
8592 | 2190 | larr |
8593 | 2191 | uarr |
8594 | 2192 | rarr |
8595 | 2193 | darr |
8596 | 2194 | harr |
8629 | 21b5 | crarr |
8656 | 21d0 | lArr |
8657 | 21d1 | uArr |
8658 | 21d2 | rArr |
8659 | 21d3 | dArr |
8660 | 21d4 | hArr |
8704 | 2200 | forall |
8706 | 2202 | part |
8707 | 2203 | exist |
8709 | 2205 | empty |
8711 | 2207 | nabla |
8712 | 2208 | isin |
8713 | 2209 | notin |
8715 | 220b | ni |
8719 | 220f | prod |
8721 | 2211 | sum |
8722 | 2212 | minus |
8727 | 2217 | lowast |
8730 | 221a | radic |
8733 | 221d | prop |
8734 | 221e | infin |
8736 | 2220 | ang |
8743 | 2227 | and |
8744 | 2228 | or |
8745 | 2229 | cap |
8746 | 222a | cup |
8747 | 222b | int |
8756 | 2234 | there4 |
8764 | 223c | sim |
8773 | 2245 | cong |
8776 | 2248 | asymp |
8800 | 2260 | ne |
8801 | 2261 | equiv |
8804 | 2264 | le |
8805 | 2265 | ge |
8834 | 2282 | sub |
8835 | 2283 | sup |
8836 | 2284 | nsub |
8838 | 2286 | sube |
8839 | 2287 | supe |
8853 | 2295 | oplus |
8855 | 2297 | otimes |
8869 | 22a5 | perp |
8901 | 22c5 | sdot |
8968 | 2308 | lceil |
8969 | 2309 | rceil |
8970 | 230a | lfloor |
8971 | 230b | rfloor |
9001 | 2329 | lang |
9002 | 232a | rang |
9674 | 25ca | loz |
9824 | 2660 | spades |
9827 | 2663 | clubs |
9829 | 2665 | hearts |
9830 | 2666 | diams |
34 | 22 | quot |
38 | 26 | amp |
60 | 3c | lt |
62 | 3e | gt |
338 | 152 | OElig |
339 | 153 | oelig |
352 | 160 | Scaron |
353 | 161 | scaron |
376 | 178 | Yuml |
710 | 2c6 | circ |
732 | 2dc | tilde |
8194 | 2002 | ensp |
8195 | 2003 | emsp |
8201 | 2009 | thinsp |
8204 | 200c | zwnj |
8205 | 200d | zwj |
8206 | 200e | lrm |
8207 | 200f | rlm |
8211 | 2013 | ndash |
8212 | 2014 | mdash |
8216 | 2018 | lsquo |
8217 | 2019 | rsquo |
8218 | 201a | sbquo |
8220 | 201c | ldquo |
8221 | 201d | rdquo |
8222 | 201e | bdquo |
8224 | 2020 | dagger |
8225 | 2021 | Dagger |
8240 | 2030 | permil |
8249 | 2039 | lsaquo |
8250 | 203a | rsaquo |
8364 | 20ac | euro |
ついでにDTD
<!ENTITY nbsp " "> <!ENTITY iexcl "¡"> <!ENTITY cent "¢"> <!ENTITY pound "£"> <!ENTITY curren "¤"> <!ENTITY yen "¥"> <!ENTITY brvbar "¦"> <!ENTITY sect "§"> <!ENTITY uml "¨"> <!ENTITY copy "©"> <!ENTITY ordf "ª"> <!ENTITY laquo "«"> <!ENTITY not "¬"> <!ENTITY shy "­"> <!ENTITY reg "®"> <!ENTITY macr "¯"> <!ENTITY deg "°"> <!ENTITY plusmn "±"> <!ENTITY sup2 "²"> <!ENTITY sup3 "³"> <!ENTITY acute "´"> <!ENTITY micro "µ"> <!ENTITY para "¶"> <!ENTITY middot "·"> <!ENTITY cedil "¸"> <!ENTITY sup1 "¹"> <!ENTITY ordm "º"> <!ENTITY raquo "»"> <!ENTITY frac14 "¼"> <!ENTITY frac12 "½"> <!ENTITY frac34 "¾"> <!ENTITY iquest "¿"> <!ENTITY Agrave "À"> <!ENTITY Aacute "Á"> <!ENTITY Acirc "Â"> <!ENTITY Atilde "Ã"> <!ENTITY Auml "Ä"> <!ENTITY Aring "Å"> <!ENTITY AElig "Æ"> <!ENTITY Ccedil "Ç"> <!ENTITY Egrave "È"> <!ENTITY Eacute "É"> <!ENTITY Ecirc "Ê"> <!ENTITY Euml "Ë"> <!ENTITY Igrave "Ì"> <!ENTITY Iacute "Í"> <!ENTITY Icirc "Î"> <!ENTITY Iuml "Ï"> <!ENTITY ETH "Ð"> <!ENTITY Ntilde "Ñ"> <!ENTITY Ograve "Ò"> <!ENTITY Oacute "Ó"> <!ENTITY Ocirc "Ô"> <!ENTITY Otilde "Õ"> <!ENTITY Ouml "Ö"> <!ENTITY times "×"> <!ENTITY Oslash "Ø"> <!ENTITY Ugrave "Ù"> <!ENTITY Uacute "Ú"> <!ENTITY Ucirc "Û"> <!ENTITY Uuml "Ü"> <!ENTITY Yacute "Ý"> <!ENTITY THORN "Þ"> <!ENTITY szlig "ß"> <!ENTITY agrave "à"> <!ENTITY aacute "á"> <!ENTITY acirc "â"> <!ENTITY atilde "ã"> <!ENTITY auml "ä"> <!ENTITY aring "å"> <!ENTITY aelig "æ"> <!ENTITY ccedil "ç"> <!ENTITY egrave "è"> <!ENTITY eacute "é"> <!ENTITY ecirc "ê"> <!ENTITY euml "ë"> <!ENTITY igrave "ì"> <!ENTITY iacute "í"> <!ENTITY icirc "î"> <!ENTITY iuml "ï"> <!ENTITY eth "ð"> <!ENTITY ntilde "ñ"> <!ENTITY ograve "ò"> <!ENTITY oacute "ó"> <!ENTITY ocirc "ô"> <!ENTITY otilde "õ"> <!ENTITY ouml "ö"> <!ENTITY divide "÷"> <!ENTITY oslash "ø"> <!ENTITY ugrave "ù"> <!ENTITY uacute "ú"> <!ENTITY ucirc "û"> <!ENTITY uuml "ü"> <!ENTITY yacute "ý"> <!ENTITY thorn "þ"> <!ENTITY yuml "ÿ"> <!ENTITY fnof "ƒ"> <!ENTITY Alpha "Α"> <!ENTITY Beta "Β"> <!ENTITY Gamma "Γ"> <!ENTITY Delta "Δ"> <!ENTITY Epsilon "Ε"> <!ENTITY Zeta "Ζ"> <!ENTITY Eta "Η"> <!ENTITY Theta "Θ"> <!ENTITY Iota "Ι"> <!ENTITY Kappa "Κ"> <!ENTITY Lambda "Λ"> <!ENTITY Mu "Μ"> <!ENTITY Nu "Ν"> <!ENTITY Xi "Ξ"> <!ENTITY Omicron "Ο"> <!ENTITY Pi "Π"> <!ENTITY Rho "Ρ"> <!ENTITY Sigma "Σ"> <!ENTITY Tau "Τ"> <!ENTITY Upsilon "Υ"> <!ENTITY Phi "Φ"> <!ENTITY Chi "Χ"> <!ENTITY Psi "Ψ"> <!ENTITY Omega "Ω"> <!ENTITY alpha "α"> <!ENTITY beta "β"> <!ENTITY gamma "γ"> <!ENTITY delta "δ"> <!ENTITY epsilon "ε"> <!ENTITY zeta "ζ"> <!ENTITY eta "η"> <!ENTITY theta "θ"> <!ENTITY iota "ι"> <!ENTITY kappa "κ"> <!ENTITY lambda "λ"> <!ENTITY mu "μ"> <!ENTITY nu "ν"> <!ENTITY xi "ξ"> <!ENTITY omicron "ο"> <!ENTITY pi "π"> <!ENTITY rho "ρ"> <!ENTITY sigmaf "ς"> <!ENTITY sigma "σ"> <!ENTITY tau "τ"> <!ENTITY upsilon "υ"> <!ENTITY phi "φ"> <!ENTITY chi "χ"> <!ENTITY psi "ψ"> <!ENTITY omega "ω"> <!ENTITY thetasym "ϑ"> <!ENTITY upsih "ϒ"> <!ENTITY piv "ϖ"> <!ENTITY bull "•"> <!ENTITY hellip "…"> <!ENTITY prime "′"> <!ENTITY Prime "″"> <!ENTITY oline "‾"> <!ENTITY frasl "⁄"> <!ENTITY weierp "℘"> <!ENTITY image "ℑ"> <!ENTITY real "ℜ"> <!ENTITY trade "™"> <!ENTITY alefsym "ℵ"> <!ENTITY larr "←"> <!ENTITY uarr "↑"> <!ENTITY rarr "→"> <!ENTITY darr "↓"> <!ENTITY harr "↔"> <!ENTITY crarr "↵"> <!ENTITY lArr "⇐"> <!ENTITY uArr "⇑"> <!ENTITY rArr "⇒"> <!ENTITY dArr "⇓"> <!ENTITY hArr "⇔"> <!ENTITY forall "∀"> <!ENTITY part "∂"> <!ENTITY exist "∃"> <!ENTITY empty "∅"> <!ENTITY nabla "∇"> <!ENTITY isin "∈"> <!ENTITY notin "∉"> <!ENTITY ni "∋"> <!ENTITY prod "∏"> <!ENTITY sum "∑"> <!ENTITY minus "−"> <!ENTITY lowast "∗"> <!ENTITY radic "√"> <!ENTITY prop "∝"> <!ENTITY infin "∞"> <!ENTITY ang "∠"> <!ENTITY and "∧"> <!ENTITY or "∨"> <!ENTITY cap "∩"> <!ENTITY cup "∪"> <!ENTITY int "∫"> <!ENTITY there4 "∴"> <!ENTITY sim "∼"> <!ENTITY cong "≅"> <!ENTITY asymp "≈"> <!ENTITY ne "≠"> <!ENTITY equiv "≡"> <!ENTITY le "≤"> <!ENTITY ge "≥"> <!ENTITY sub "⊂"> <!ENTITY sup "⊃"> <!ENTITY nsub "⊄"> <!ENTITY sube "⊆"> <!ENTITY supe "⊇"> <!ENTITY oplus "⊕"> <!ENTITY otimes "⊗"> <!ENTITY perp "⊥"> <!ENTITY sdot "⋅"> <!ENTITY lceil "⌈"> <!ENTITY rceil "⌉"> <!ENTITY lfloor "⌊"> <!ENTITY rfloor "⌋"> <!ENTITY lang "〈"> <!ENTITY rang "〉"> <!ENTITY loz "◊"> <!ENTITY spades "♠"> <!ENTITY clubs "♣"> <!ENTITY hearts "♥"> <!ENTITY diams "♦"> <!ENTITY quot """> <!ENTITY amp "&"> <!ENTITY lt "<"> <!ENTITY gt ">"> <!ENTITY OElig "Œ"> <!ENTITY oelig "œ"> <!ENTITY Scaron "Š"> <!ENTITY scaron "š"> <!ENTITY Yuml "Ÿ"> <!ENTITY circ "ˆ"> <!ENTITY tilde "˜"> <!ENTITY ensp " "> <!ENTITY emsp " "> <!ENTITY thinsp " "> <!ENTITY zwnj "‌"> <!ENTITY zwj "‍"> <!ENTITY lrm "‎"> <!ENTITY rlm "‏"> <!ENTITY ndash "–"> <!ENTITY mdash "—"> <!ENTITY lsquo "‘"> <!ENTITY rsquo "’"> <!ENTITY sbquo "‚"> <!ENTITY ldquo "“"> <!ENTITY rdquo "”"> <!ENTITY bdquo "„"> <!ENTITY dagger "†"> <!ENTITY Dagger "‡"> <!ENTITY permil "‰"> <!ENTITY lsaquo "‹"> <!ENTITY rsaquo "›"> <!ENTITY euro "€">